Python-Federated-API-SAML-ADFS

auth.py

#based on https://aws.amazon.com/blogs/security/how-to-implement-federated-api-and-cli-access-using-saml-2-0-and-ad-fs/

import sys
import boto.sts
import boto.s3
import requests
import ConfigParser
import base64
import logging
import os
import xml.etree.ElementTree as ET
import re
from bs4 import BeautifulSoup
from os.path import expanduser
from urlparse import urlparse
import xml.dom.minidom

    # region: The default AWS region that this script will connect to for all API calls
    # Set AWS_ADFS_URL and AWS_ADFS_SESSION_TIMEOUT
    region      = "<Your aws region>"
    username    = "<Your domain user name>"
    password    = "<Your password>"
    profilename = "<Your profile name>"
    
    # output format: The AWS CLI output format that will be configured in the
    # saml profile (affects subsequent CLI calls)
    outputformat = 'json'

    # awsconfigfile: The file where this script will store the temp
    # credentials under the saml profile
    awsconfigfile = '/.aws/credentials'

    # SSL certificate verification: Whether or not strict certificate
    # verification is done, False should only be used for dev/test
    sslverification = True

    default_creds_file = expanduser("~") + awsconfigfile

    exists = os.path.isfile(default_creds_file)

    if exists:
        credentials = open(default_creds_file, "r").read()
        if "[default]" not in credentials:
            print "You need to have the default credentials configured even if the values are empty"
            exit(1)
    else:
        print "You need to create the credentials file in your home directory"
        exit(1)

    # idpentryurl: The initial url that starts the authentication process.
    #idpentryurl = 'https://<fqdn>:<port>/adfs/ls/IdpInitiatedSignOn.aspx?loginToRp=urn:amazon:webservices'
    try:
        idpentryurl = os.environ['AWS_ADFS_URL']
    except KeyError:
        print "You need to set the AWS_ADFS_URL to a valid https URL"
        exit(1)

    print "Using AWS_ADFS_URL: " + idpentryurl

    try:
        session_timeout = os.environ['AWS_ADFS_SESSION_TIMEOUT']
    except KeyError:
        print "Session Time out is not set. Using the default of 60 minutes"
        session_timeout = 3600

    # Uncomment to enable low level debugging
    logging.basicConfig(level=logging.INFO)

    ##########################################################################

    # Initiate session handler
    session = requests.Session()

    # Programmatically get the SAML assertion
    # Opens the initial IdP url and follows all of the HTTP302 redirects, and
    # gets the resulting login page
    formresponse = session.get(idpentryurl, verify=sslverification)
    # Capture the idpauthformsubmiturl, which is the final url after all the 302s
    idpauthformsubmiturl = formresponse.url

    # Parse the response and extract all the necessary values
    # in order to build a dictionary of all of the form values the IdP expects
    #formsoup = BeautifulSoup(formresponse.text.decode('utf8'))
    formsoup = BeautifulSoup(formresponse.text.decode('utf8'),"html.parser")
    payload = {}

    for inputtag in formsoup.find_all(re.compile('(INPUT|input)')):
        name = inputtag.get('name','')
        value = inputtag.get('value','')
        if "user" in name.lower():
            #Make an educated guess that this is the right field for the username
            payload[name] = username
        elif "email" in name.lower():
            #Some IdPs also label the username field as 'email'
            payload[name] = username
        elif "pass" in name.lower():
            #Make an educated guess that this is the right field for the password
            payload[name] = password
        else:
            #Simply populate the parameter with the existing value (picks up hidden fields in the login form)
            payload[name] = value

    # Debug the parameter payload if needed
    # Use with caution since this will print sensitive output to the screen
    #print payload

    # Some IdPs don't explicitly set a form action, but if one is set we should
    # build the idpauthformsubmiturl by combining the scheme and hostname
    # from the entry url with the form action target
    # If the action tag doesn't exist, we just stick with the
    # idpauthformsubmiturl above
    for inputtag in formsoup.find_all(re.compile('(FORM|form)')):
        action = inputtag.get('action')
        loginid = inputtag.get('id')
        if (action and loginid == "loginForm"):
            parsedurl = urlparse(idpentryurl)
            idpauthformsubmiturl = parsedurl.scheme + "://" + parsedurl.netloc + action

    # Performs the submission of the IdP login form with the above post data
    response = session.post(
        idpauthformsubmiturl, data=payload, verify=sslverification)

    # Debug the response if needed
    #print (response.text)

    # Overwrite and delete the credential variables, just for safety
    username = '##############################################'
    password = '##############################################'
    del username
    del password

    # Decode the response and extract the SAML assertion
    soup = BeautifulSoup(response.text.decode('utf8'), "html.parser")
    assertion = ''


    # Look for the SAMLResponse attribute of the input tag (determined by
    # analyzing the debug print lines above)
    for inputtag in soup.find_all('input'):
        if(inputtag.get('name') == 'SAMLResponse'):
            #print(inputtag.get('value'))
            assertion = inputtag.get('value')

    # Better error handling is required for production use.
    if (assertion == ''):
        #TODO: Insert valid error checking/handling
        label = soup.find(id='errorText')
        print label.string
        print '------------'
        print 'Response did not contain a valid SAML assertion'
        sys.exit(1)

    # Debug only
    xml = xml.dom.minidom.parseString(base64.b64decode(assertion)) # or xml.dom.minidom.parseString(xml_string)
    print xml.toprettyxml()

    # Parse the returned assertion and extract the authorized roles
    awsroles = []
    root = ET.fromstring(base64.b64decode(assertion))
    for saml2attribute in root.iter('{urn:oasis:names:tc:SAML:2.0:assertion}Attribute'):
        if (saml2attribute.get('Name') == 'https://aws.amazon.com/SAML/Attributes/Role'):
            for saml2attributevalue in saml2attribute.iter('{urn:oasis:names:tc:SAML:2.0:assertion}AttributeValue'):
                awsroles.append(saml2attributevalue.text)

    # Note the format of the attribute value should be role_arn,principal_arn
    # but lots of blogs list it as principal_arn,role_arn so let's reverse
    # them if needed
    for awsrole in awsroles:
        chunks = awsrole.split(',')
        if'saml-provider' in chunks[0]:
            newawsrole = chunks[1] + ',' + chunks[0]
            index = awsroles.index(awsrole)
            awsroles.insert(index, newawsrole)
            awsroles.remove(awsrole)

    # If I have more than one role, ask the user which one they want,
    # otherwise just proceed
    print ""
    if len(awsroles) > 1:
        i = 0
        print "Please choose the role you would like to assume:"
        for awsrole in awsroles:
            print '[', i, ']: ', awsrole.split(',')[0]
            i += 1
        print "Selection: ",
        selectedroleindex = raw_input()

        # Basic sanity check of input
        if int(selectedroleindex) > (len(awsroles) - 1):
            print 'You selected an invalid role index, please try again'
            sys.exit(0)

        role_arn = awsroles[int(selectedroleindex)].split(',')[0]
        principal_arn = awsroles[int(selectedroleindex)].split(',')[1]
    else:
        role_arn = awsroles[0].split(',')[0]
        principal_arn = awsroles[0].split(',')[1]

    # Use the assertion to get an AWS STS token using Assume Role with SAML
    #print boto.sts.regions()
    conn = boto.sts.connect_to_region(region)
    #print conn.__dict__
    token = conn.assume_role_with_saml(role_arn, principal_arn, assertion,None, int(session_timeout))


    # Write the AWS STS token into the AWS credential file
    home = expanduser("~")
    filename = home + awsconfigfile

    # Read in the existing config file
    config = ConfigParser.RawConfigParser()
    config.read(filename)

    # Put the credentials into a saml specific section instead of clobbering
    # the default credentials
    if not config.has_section(profilename):
        config.add_section(profilename)

    config.set(profilename,'output', outputformat)
    config.set(profilename,'region', region)
    config.set(profilename,'aws_access_key_id', token.credentials.access_key)
    config.set(profilename,'aws_secret_access_key', token.credentials.secret_key)
    config.set(profilename,'aws_session_token', token.credentials.session_token)

    # Write the updated config file
    with open(filename, 'w+') as configfile:
        config.write(configfile)

    # Give the user some basic info as to what has just happened
    print '\n\n----------------------------------------------------------------'
    print 'Your new access key pair has been stored in the AWS configuration file {0} under the saml profile.'.format(filename)
    print 'Note that it will expire at {0}.'.format(token.credentials.expiration, '%Y-%M-%s')
    print 'After this time, you may safely rerun this script to refresh your access key pair.'
    print 'To use this credential, call the AWS CLI with the --profile option (e.g. aws --profile saml ec2 describe-instances).'
    print '----------------------------------------------------------------\n\n'